Kimi K2.5/K2.6 1T — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on Kimi K2.5/K2.6 1T. Owning-hyperscaler TCO normalized by output tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
B200 edges MI325X at 40 tok/s/user on Kimi K2.5/K2.6 1T — $1.04 per million tokens versus $4.03, a 288% cost-per-token gap.
Push Kimi K2.5/K2.6 1T to 44 tok/s/user and B200 lands at $1.14 per million tokens against MI325X's $4.99 — B200 pulls ahead by 337%.
B200: $1.25 per million tokens. MI325X: $6.10. Both at 48 tok/s/user on Kimi K2.5/K2.6 1T, with B200 388% cheaper. (Numbers reflect the default 1k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · MI325X $1.28/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B200:$1.038MI325X:$4.028 | B200:$1.140MI325X:$4.986 | B200:$1.251MI325X:$6.102 |
| Concurrency | B200:~55MI325X:~9 | B200:~46MI325X:~7 | B200:~38MI325X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.